paper-with-me

Papers

Graph Neural Networks for Multiparallel Word Alignment

2022-03-16 · Findings (ACL) 2022 5 · Ayyoob Imani, Lütfi Kerem Şenel, Masoud Jalili Sabet, François Yvon, Hinrich Schütze

After a period of decrease, interest in word alignments is increasing again for their usefulness in domains such as typological research, cross-lingual annotation projection, and machine translation. Generally, alignment algorithms only use bitext and do not make use of the fact that many parallel corpora are multiparallel. Here, we compute high-quality word alignments between multiple language pairs by considering all language pairs together. First, we create a multiparallel word alignment graph, joining all bilingual word alignment pairs in one graph. Next, we use graph neural networks (GNNs) to exploit the graph structure. Our GNN approach (i) utilizes information about the meaning, position, and language of the input words, (ii) incorporates information from multiple parallel sentences, (iii) adds and removes edges from the initial alignments, and (iv) yields a prediction model that can generalize beyond the training sentences. We show that community detection provides valuable information for multiparallel word alignment. Our method outperforms previous work on three word-alignment datasets and on a downstream task.

📄 PDF Abstract BibTeX arXiv:2203.08654

Code (0)

등록된 구현이 없습니다.

Tasks

Community DetectionMachine TranslationTranslationWord Alignment

Similar Papers 제목 키워드 기반

Graph Neural Networks for Multiparallel Word Alignment

2021-11-16 · ACL ARR September 2021 9 · Anonymous

After a period of decrease, interest in word alignments is increasing again for their usefulness in domains such as typological research, cross-lingual annotation projection and machine translation. Generally, alignment …

Community DetectionMachine TranslationWord Alignment

Graph Algorithms for Multiparallel Word Alignment

2021-09-13 · EMNLP 2021 11 · Ayyoob Imani, Masoud Jalili Sabet, Lütfi Kerem Şenel, Philipp Dufter 외

With the advent of end-to-end deep learning approaches in machine translation, interest in word alignments initially decreased; however, they have again become a focus of research more recently. Alignments are useful for…

Link PredictionMachine TranslationRecommendation SystemsTranslation+1

Assessing the Political Fairness of Multilingual LLMs: A Case Study based on a 21-way Multiparallel EuroParl Dataset

2025-10-23 · Paul Lerner, François Yvon arxiv

The political biases of Large Language Models (LLMs) are usually assessed by simulating their answers to English surveys. In this work, we propose an alternative framing of political biases, relying on principles of fair…

Monolingual alignment of word senses and definitions in lexicographical resources

2022-09-06 · Sina Ahmadi

The focus of this thesis is broadly on the alignment of lexicographical data, particularly dictionaries. In order to tackle some of the challenges in this field, two main tasks of word sense alignment and translation inf…

Semantic SimilaritySemantic Textual SimilarityTranslation

Dijkstra-WSA: A Graph-Based Approach to Word Sense Alignment

2013-01-01 · TACL 2013 1 · Michael Matuschek, Iryna Gurevych

In this paper, we present Dijkstra-WSA, a novel graph-based algorithm for word sense alignment. We evaluate it on four different pairs of lexical-semantic resources with different characteristics (WordNet-OmegaWiki, Word…

Semantic ParsingSemantic Role LabelingWord Sense Disambiguation